make-a-deck
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate HTML and CSS files, creating a surface where malicious instructions in the input could influence the agent's behavior during the file creation process.
- Ingestion points: The 'Intake' section in
SKILL.mdidentifies user-provided data such as deck topic, audience, delivery mode, and brand context as primary inputs. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when handling user-provided content.
- Capability inventory: The skill possesses file-write capabilities, specifically writing to the
./opendesign/mockups/<task-slug>/directory. - Sanitization: There are no explicit instructions for the agent to sanitize, escape, or validate the external content before interpolating it into the final slide output.
Audit Metadata